Google OSS Expert Prize: March Winners Announcement

[Kaggle] Hi {NAME}, The Kaggle community has tremendous expertise regarding [Google's open source ML software ecosystem]( and this prize is intended to celebrate some of our favorite recently shared tutorials. Each month, up to three authors are selected for this award. April 2022 Google OSS Expert Prize Winners - @spsayakpaul's notebook ["Distilling Vision Transformers"]( demonstrates how a technique called [knowledge distillation]( can be implemented using [Keras](. This approach takes inductive biases learned by a teacher model (BiT) and then transfers them to a student model (ViT) . We were particularly impressed at how easy it was to read and understand the well organized code. - In @roguekk007's notebook [[Pytorch-friendly] Comprehensive JAX+TPU Intro]( the author takes an [EfficientNetV2]( model (developed by Google Research) from [PyTorch Hub](, ports it to [JAX](, and then fine-tunes it against the ["Petals to the Metal"]( Kaggle dataset. The markdown cells and the code comments are detailed and provide insights not only about the code but also about the process of learning to code with JAX on TPUs. Honorable Mention - @aritrag and @ritzraha's notebook [3D volumetric rendering with NeRF]( use [TensorFlow]( to train a [NeRF model]( capable of generating 3-dimensional reconstructions given 2-dimensional image inputs. These types of methods are useful for applications that require spatial awareness such as mapping and/or navigation and control of autonomous robots/vehicles, etc. - @sauravmaheshkar and @soumikrakshit take a slightly different approach and instead use [JAX/FLAX]( to train their [NeRF model]( in the notebook ["[Jax + Flax] Minimal Implementation of NeRF"](. We really liked being able to compare this JAX implementation to the TensorFlow implementation above. You can be recognized yourself for the April 2022 [Google OSS prize](. To be considered, submit public content to Kaggle that makes use of Google's open source ML software ecosystem (e.g. TensorFlow, JAX, etc) [here](. Best wishes, The Kaggle Team Kaggle, Inc 1600 Amphitheatre Pkwy Mountain View, CA 94043 This email was sent to {EMAIL} because you indicated that you'd like to receive news and updates about Kaggle. If you don't want to receive these emails in the future, please [unsubscribe here](. You can also change your preferences on your account's profile page by logging in at [kaggle.com.](